Power distribution network (PDN) optimization in 2.5-D chiplet architectures represents a critical bottleneck as designs scale to 100+ integrated chiplets, where decoupling capacitor placement becomes a multi-port optimization challenge requiring millions of expensive electromagnetic (EM) simulations. Current state-of-the-art (SOTA) methods - from genetic algorithms (GA) to reinforcement learning (RL) - treat PDN as black-box functions, failing to exploit inherent physical structure and scaling exponentially with problem complexity. We introduce Φ-BO, the first physics-informed Bayesian optimization (BO) framework specifically designed for multi-port decoupling capacitor placement in 2.5-D chiplet PDN. Our key innovation systematically integrates EM field theory into machine learning (ML) optimization through novel spatial feature transformations and Multi-Port Aware Transformation (MPAT), enabling a paradigm shift from black-box to physics-aware optimization. This approach captures spatial dependencies and port coupling effects, dramatically reducing effective problem dimensionality while enabling intelligent exploration of discrete placement configurations. Demonstrated on a 22-chiplet RISC-V processor design, Φ-BO achieves 23% impedance improvement, and 3 × faster convergence compared to SOTA methods.

Heterogeneous 3D integration technology is a cost-effective and high-performance alternative to planar integrated circuits (ICs). In this paper, we propose an on-chip power distribution network (PDN) modeling technique for heterogeneous 3D-ICs (H3D-ICs), which explicitly takes the effects of on-chip inductance into account. The proposed model facilitates efficient transient and AC simulations with integrated inductive effects, enabling accurate noise characterization at high frequencies and facilitating the exploration of early-stage PDN design. The model is validated via HSPICE simulations, demonstrating a maximum error below 1% and achieving average speedups of 1.5x in transient and 8.5x in AC simulations.

Textual label names (descriptions) are typically semantically rich in many natural language understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which is widely used to enrich model input, into the label side for the first time. Specifically, we propose a Mask Matching method, which equips an input with a prompt and its label with another, and then makes predictions by matching their mask representations. We evaluate our method extensively on 8 NLU tasks with 14 datasets. The experimental results show that Mask Matching significantly outperforms its counterparts of fine-tuning and conventional prompt-tuning, setting up state-of-the-art performances in several datasets. Mask Matching is particularly good at handling NLU tasks with large label counts and informative label names. As pioneering efforts that investigate the label-side prompt, we also discuss open issues for future study.

Semantic similarity between two sentences is inherently subjective and can vary significantly based on the specific aspects emphasized.Consequently, traditional sentence encoders must be capable of generating conditioned sentence representations that account for diverse conditions or aspects.In this paper, we propose a novel yet efficient framework based on transformer-style language models that facilitates advanced conditioned sentence representation while maintaining model parameters and computational efficiency.Empirical evaluations on the Conditional Semantic Textual Similarity and Knowledge Graph Completion tasks demonstrate the superiority of our proposed framework.

Twitter sentiment analysis has received interest in both industry and academia recently. It strives to analyze people’s emotions through tweets, which is an important part of natural language processing. However, it faces some special challenges such as short texts of tweets, informal expressions, and a lack of precisely labeled data. In this paper, we present a novel data augmentation method called Enhanced Mixup, which is able to generate additional labeled data by using the current instance and other instances of the original training data. Furthermore, we present a simple convolutional neural network that leverages Enhanced Mixup and Transfer Learning (termed as EMTCNN) for Twitter sentiment analysis. We also conducted a series of ablation experiments to verify the effectiveness of our proposed techniques. Finally, we evaluate our model on five standard public Twitter datasets. The results demonstrate that EMTCNN can reach new state-of-the-art in all of them without using any external lexicons or feature engineering.